82
1

Robust random graph matching in dense graphs via vector approximate message passing

Abstract

In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence. We are particularly interested in a robust version of this problem such that our observation is a perturbed input (A+E,B+F)(A+E,B+F) where (A,B)(A,B) is a pair of correlated Gaussian Wigner matrices and E,FE,F are adversarially chosen matrices supported on an unknown ϵnϵn\epsilon n * \epsilon n principle minor of A,BA,B, respectively. We propose a vector-approximate message passing (vector-AMP) algorithm that succeeds in polynomial time as long as the correlation ρ\rho between (A,B)(A,B) is a non-vanishing constant and ϵ=o(1(logn)20)\epsilon = o\big( \tfrac{1}{(\log n)^{20}} \big). The main methodological inputs for our result are the iterative random graph matching algorithm proposed in \cite{DL22+, DL23+} and the spectral cleaning procedure proposed in \cite{IS24+}. To the best of our knowledge, our algorithm is the first efficient random graph matching type algorithm that is robust under any adversarial perturbations of n1o(1)n^{1-o(1)} size.

View on arXiv
Comments on this paper